Manifold Topology Divergence: a Framework for Comparing Data Manifolds - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Advances in Neural Information Processing Systems Année : 2021

Manifold Topology Divergence: a Framework for Comparing Data Manifolds

Résumé

We develop a framework for comparing data manifolds, aimed, in particular, towards the evaluation of deep generative models. We describe a novel tool, Cross-Barcode(P,Q), that, given a pair of distributions in a high-dimensional space, tracks multiscale topology spacial discrepancies between manifolds on which the distributions are concentrated. Based on the Cross-Barcode, we introduce the Manifold Topology Divergence score (MTop-Divergence) and apply it to assess the performance of deep generative models in various domains: images, 3D-shapes, time-series, and on different datasets: MNIST, Fashion MNIST, SVHN, CIFAR10, FFHQ, chest X-ray images, market stock data, ShapeNet. We demonstrate that the MTop-Divergence accurately detects various degrees of mode-dropping, intra-mode collapse, mode invention, and image disturbance. Our algorithm scales well (essentially linearly) with the increase of the dimension of the ambient high-dimensional space. It is one of the first TDA-based practical methodologies that can be applied universally to datasets of different sizes and dimensions, including the ones on which the most recent GANs in the visual domain are trained. The proposed method is domain agnostic and does not rely on pre-trained networks.
Fichier principal
Vignette du fichier
MTDivergenceArxive (7).pdf (1.97 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03418125 , version 1 (06-11-2021)

Identifiants

Citer

Serguei Barannikov, Ilya Trofimov, Grigorii Sotnikov, Ekaterina Trimbach, Alexander Korotin, et al.. Manifold Topology Divergence: a Framework for Comparing Data Manifolds. Advances in Neural Information Processing Systems, 2021. ⟨hal-03418125⟩
36 Consultations
40 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More